People flow analysis apparatus, people flow analysis method, and storage medium

Abstract

An image processing apparatus includes a measurement area setting unit that sets a measurement area in an input image, a small image setting unit that sets a small image in the input image based on the measurement area, a first estimation unit that estimates a flow distribution of a target in the small image, and a second estimation unit that estimates the number of targets to pass through the measurement area based on the flow distribution in the small image.

What is claimed is: 
     
       1. An image processing apparatus comprising:
 a processor; and 
 a memory storing executable instructions which, when executed by the processor, cause the image processing apparatus to perform operations including: 
 setting a measurement area in an image; 
 acquiring a plurality of small images overlapping with the measurement area from the image, wherein the plurality of small images each includes a margin area and a central area, wherein a width of the margin area is determined based on size of a target object, and wherein central areas of the adjacent small images are in contact with each other; 
 extracting positions of target objects included in the central area of the small image based on a density distribution estimated based on the small images; and 
 estimating a number of target objects passing through the measurement area based on the positions of the target objects included in the central area of the small image. 
 
     
     
       2. The image processing apparatus according to  claim 1 , wherein the measurement area is set based on a reference figure. 
     
     
       3. The image processing apparatus according to  claim 1 , wherein the plurality of small images is divided from the image based on the measurement area. 
     
     
       4. The image processing apparatus according to  claim 1 , wherein the measurement area is an area specified by a user. 
     
     
       5. The image processing apparatus according to  claim 1 , wherein the image is acquired from a solid-state image sensing device. 
     
     
       6. The image processing apparatus according to  claim 1 , wherein the image is acquired from a storage device. 
     
     
       7. The image processing apparatus according to  claim 1 , wherein executing the executable instructions causes the information processing apparatus to further perform operations including outputting the number of targets. 
     
     
       8. The image processing apparatus according to  claim 7 , wherein the measurement area is output. 
     
     
       9. The image processing apparatus according to  claim 7 , wherein a position of the small images is output. 
     
     
       10. The image processing apparatus according to  claim 1 , wherein the positions of the target objects are determined by estimating a flow distribution of target object in the small image. 
     
     
       11. The image processing apparatus according to  claim 1 , wherein the number of the target objects passing through the measurement area is estimated based on an extended measurement area that is obtained by extending the measurement area. 
     
     
       12. An image processing method comprising:
 setting a measurement area in an image; 
 acquiring a plurality of small images overlapping with the measurement area from the image, wherein the plurality of small images each includes a margin area and a central area, wherein a width of the margin area is determined based on size of a target object, and wherein central areas of the adjacent small images are in contact with each other; 
 extracting positions of target objects included in the central area of the small image based on a density distribution estimated based on the small images; and 
 estimating a number of thc target objects passing through the measurement area based on the positions of the target objects included in the central area of the small image. 
 
     
     
       13. A non-transitory computer—readable storage medium storing a program for causing a computer to:
 set a measurement area in an image; 
 acquire a plurality of small images overlapping with the measurement area from the image, wherein the plurality of small images each includes a margin area and a central area, wherein a width of the margin area is determined based on size of a target object, and wherein central areas of the adjacent small images are in contact with each other; 
 extract positions of target objects included in the central area of the small image based on a density distribution estimated based on the small images; and 
 estimate a number of target objects passing through the measurement area based on the positions of the target objects included in the central area of the small image.